Write or paste text
Use a script, app message, or LLM draft.
Expressive text-to-speech
Great text-to-speech for LLM apps, videos, games, and products
Create polished voice output in minutes. Write natural text, add simple tone tags, reuse the same voice across every prompt, and let your LLM app generate audio through MCP when you want hands-off workflows.
Add tone tagsSave voicesConnect LLM apps
USER
Write a warm dashboard update.
ASSISTANT
[warm] Welcome back. [excited] Report ready.
Studio previewaudio ready
Voice: Product Guide v2 Tone tags: [calm], [bright] Use for: dashboard updates Output: audio ready
Easy workflow
From text to polished audio without fiddly voice prompts
The workflow is simple enough for a creator and structured enough for a product team. Start in the studio, then reuse the same tags and saved voices from your app or LLM workflow.
Add tone in brackets
Try [quiet], [excited], or [loud and angry].
Pick a saved voice
Templates keep every prompt consistent.
Generate audio
Preview in the UI or hand it to your app.
Why teams choose it
Easy to start, good enough to keep using
Make great speech quickly, keep voices consistent, and let humans or LLM apps use the same simple setup.
Sounds intentional
Expression tags make emotion, pacing, and emphasis clear, so speech feels directed instead of guessed.
Stays consistent
Voice templates keep your narrator, character, support voice, or course instructor recognizable across many prompts.
Easy for LLM users
Connect once, choose the voices your app may use, and ask your LLM workflow to create audio from approved text.
Ready for teams
Plans, top-ups, spend caps, and workspaces help you move from one test to shared production use without surprise bills.
Popular workflows
Voice workflows for games, videos, agents, and learning
Start in the UI, connect an LLM app through MCP, or move the same workflow into the API when it becomes part of your product.
Create voices for your own game
Prototype NPC dialogue, mission updates, tutorials, and character barks with saved voice templates.
Narrate YouTube videos
Turn scripts, outlines, and LLM drafts into consistent narration for tutorials, explainers, and Shorts.
Give AI agents voice output
Let agents validate markup, estimate credits, create speech jobs, and return audio URLs through MCP.
Support voice agents
Keep customer replies clear, scoped, and on brand with workspace keys, templates, and spend caps.
Course and training narration
Create repeatable instructor voices for lessons, internal training, onboarding, and accessibility audio.
Product demos and explainers
Generate polished narration for demos, release notes, feature tours, and product education.
LLM setup
Follow a short setup guide, choose a saved voice, and ask your LLM app to create audio.
Easy LLM setup
Give your LLM app a voice tool without building an integration first
TextToSpeechSkills is made for the moment when you want an LLM to help with speech, not just write scripts. Install the MCP tool, choose which voices are allowed, and let the same workflow create narration, character lines, support replies, or product audio.
Read the guideMCP install
Paste one command into your LLM app settings.
Saved voices
Pick the narrator, character, or support voice it can use.
Tone tags
Ask for readable tags like [quiet], [excited], or [loud and angry].
Audio ready
Review the result in your dashboard or send it back to your app.
Credit pricing
Start small, then let usage scale safely
The paid Test plan includes 30 credits for $2.99. Higher tiers include monthly credits, automatic top-ups, and spend caps so overage stays predictable.
Test
$2.99
30 credits each month
- 30 economy minutes
- 15 instant minutes
- Auto top-up: 30 credits
- Cap defaults to $15
Starter
$12
300 credits each month
- 300 economy minutes
- 150 instant minutes
- Auto top-up: 250 credits
- Cap defaults to $50
Pro
Best fit$39
1,200 credits each month
- 1200 economy minutes
- 600 instant minutes
- Auto top-up: 750 credits
- Cap defaults to $150
Scale
$99
3,200 credits each month
- 3200 economy minutes
- 1600 instant minutes
- Auto top-up: 2500 credits
- Cap defaults to $500
Workspace add-on available on Pro and higher as a $2/user monthly add-on with central billing.
Studio preview
Write expression directly in the text
quietloud and angry
Markup looks good
Short scripts usually finish immediately; longer scripts appear when the audio is ready.
Expression markup
Voice direction that stays readable
Use tags like [quiet], [sad], or [loud and angry] to control delivery without hiding meaning inside long prompts.
| Tag | Category | Example | Description |
|---|---|---|---|
| quiet | volume | [quiet] hello there. | Speak softly or at a low volume. |
| whisper | volume | [whisper] I have a secret. | Use a very soft, intimate delivery. |
| loud | volume | [loud] Listen up! | Increase emphasis and volume. |
| excited | emotion | [excited] that's amazing! | Speak with high energy and enthusiasm. |
| angry | emotion | [angry] how could you do that? | Speak with anger or frustration. |
| warm | tone | [warm] welcome back. | Use a friendly and pleasant tone. |
| serious | tone | [serious] this is important. | Use a focused, earnest tone. |
| fast | pace | [fast] let's go! | Increase speaking speed. |
| slow | pace | [slow] take your time. | Decrease speaking speed. |
| pause | timing | [pause] wait here. | Insert a short pause. |
| laugh | interjection | [laugh] that's funny. | Add a brief natural laugh. |
Reusable voices
Templates keep one voice across many prompts
Save persona, tone, pacing, accent, style rules, and sample prompts as versioned assets your whole team can reuse.
| Template | Persona | Pace | Warmth | Stability |
|---|---|---|---|---|
| Calm Narrator | Clear narrator for explainers and product walkthroughs | medium | 82% | 91% |
| Energetic Coach | High-energy coach for launches and motivating clips | fast | 74% | 80% |
| Warm Teacher | Friendly teacher for lessons and onboarding | medium | 94% | 87% |
Template preview
Calm Narrator v1
Compare saved versions across multiple prompts before making a template active.